© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14952
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding social issues and cultural topics, particularly related to gender, race, and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Topics often following prepositions

    np_acts-logits-general · gemini-2.0-flash

    abstract topics following common connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verksamhet
    -0.73
     activiteiten
    -0.70
     diensten
    -0.67
     goederen
    -0.64
     oplossing
    -0.64
    tvguidetime
    -0.62
     verksam
    -0.61
     pourrez
    -0.61
     flesta
    -0.61
     modalités
    -0.60
    POSITIVE LOGITS
     identity
    0.90
     racism
    0.76
     gender
    0.76
     masculinity
    0.76
     sexism
    0.75
     globalization
    0.73
     race
    0.72
     aging
    0.72
     parenthood
    0.72
     immigration
    0.72
    Activations Density 0.379%

    No Known Activations